Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace/plugin install credoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/optimize)<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/optimize"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/optimize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/optimize"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00182 | $0.04337 |
| Opus 5.5 | $0.00073 | $0.01735 |
| Sonnet 5.5 | $0.00036 | $0.00867 |
| Haiku 4.5 | $0.00018 | $0.00434 |
Grade A, and why
optimize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
optimize - the credo optimisation audit
An audit credo OFFERS but never forces. It looks at how the repo is organised and worked on, and proposes improvements that make parallel and long-running work smoother. Every finding is a proposal; nothing changes without the user's explicit choice.
Hard rules
- Consent first. Nothing is scanned before the user said Yes (opt-in question, the
welcome-back offer, or running
/credo:optimizeby hand). Nothing is changed before the user picked Implement for that finding. - Interactive only. Findings are presented with the Ask tool (plain text when no Ask tool exists). In credo autonomous mode never run this skill and never ask: leave a pending offer pending for the next attended session.
- Read-only scan. The scan only reads: files,
git log,git status,git branch,gh pr list(whenghis available). The only write before the user's choices is the report file.git fetchin the freshness check is the only network-touching git call. - Outside the repo only with consent. The instruction-consistency check (2.6) reads the user's global instruction files outside the repo; it runs only when the user said Yes to it in this run (step 1b). It never edits any instruction file.
- Never read secrets. File NAMES of
.env*, keys or credentials may be listed (for the worktree files list), their CONTENTS are never read. - Existing conventions win. Detect what the repo already does first; recommend an ecosystem standard only where nothing exists, and let the user confirm it. Never push a convention onto a repo that has a working one.
- Language-agnostic. Use the repo's own ecosystem (package manager, test runner, CI) for every suggestion. Never invent a command that has no basis in the repo.
State and helpers
All scripts live in "${CLAUDE_PLUGIN_ROOT}/scripts/". State is per repo (the main
worktree) and per Claude Code profile, under
${CLAUDE_CONFIG_DIR:-$HOME/.claude}/credo/optimize/<repo-hash>/.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 15d ago Changed · +83 lines · +14 tokens per session 97133e2a41f2
- 17d ago First seen · 189 lines · 168 tokens per session scan A d2845af822ac
optimize is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (12 stars, last pushed yesterday), licensed MIT. It adds 182 tokens to every session and 4,337 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
customer-success
Support workflows, ticketing systems (Zendesk, Intercom), knowledge base design, chatbot design, and metrics (CSAT, NPS). Use when building support infrastructure, designing help centers, or optimizing customer experience.
event-planner
Event planning with timelines, budgets, vendor coordination, logistics checklists, and post-event evaluation. Use when organizing conferences, workshops, galas, or corporate events.
hr-talent
HR and talent management expertise for talent acquisition, performance management, compensation strategy, organizational design, culture building, succession planning, and D&I programs. Use when hiring, managing performance, designing organizations, or building culture.
leadership
Executive leadership expertise for decision-making, change management, crisis management, stakeholder management, team building, and organizational leadership. Use when leading teams, managing change, navigating crises, or developing leadership skills.
operations
Operations excellence expertise for supply chain optimization, process improvement (Lean, Six Sigma), capacity planning, vendor management, quality assurance, and operational efficiency. Use when optimizing processes, managing supply chains, or improving operational performance.
process-flowchart-designer
Create process flowcharts and workflow diagrams from descriptions, with optimization suggestions and bottleneck identification. Use when mapping processes, designing workflows, or improving operational efficiency.